helpers/skills/doc-pipeline/SKILL.md
Use this skill to orchestrate the full documentation pipeline. Sequences doc-gather, doc-gap, doc-validate, doc-review, and doc-generate skills based on the requested pipeline mode.
npx skillsauth add opendatahub-io/ai-helpers doc-pipelineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Orchestrate documentation skills in dependency order based on the requested pipeline mode.
$ARGUMENTS contains:
gather, gap, validate, review, generate (required)| Mode | Skills executed | Use case |
|---|---|---|
| gather | doc-gather | Collect context only |
| gap | doc-gather → doc-gap | Identify documentation gaps |
| validate | doc-gather → doc-validate | Validate existing docs against context |
| review | doc-gather → doc-validate → doc-review | Full validation and review of existing docs |
| generate | doc-gather → doc-gap → doc-generate → doc-validate → doc-review | Generate docs end-to-end |
${CLAUDE_SKILL_DIR}/../doc-gather/configs/rhoai.yaml existsFor each skill in the pipeline mode's sequence:
/doc-<skill> <arguments>/doc-gather <JIRA-KEY>
Report: context package summary.
/doc-gather <JIRA-KEY>
/doc-gap
Check: if gap report recommendation is stop, halt and report gaps to caller.
Report: gap report summary.
/doc-gather <JIRA-KEY>
/doc-validate <docs-directory>
The docs directory is determined from the context package (the docs repo checkout path). Report: validation findings summary.
/doc-gather <JIRA-KEY>
/doc-validate <docs-directory>
/doc-review <docs-directory>
Report: validation + review findings summary.
/doc-gather <JIRA-KEY>
/doc-gap
Gate: Check gap report recommendation.
stop: halt, report insufficient context.gather-more: warn, ask caller whether to proceed.proceed: continue./doc-generate
/doc-validate workspace/generated-docs/
/doc-review workspace/generated-docs/
Report: generation report + validation + review summaries.
After all skills complete, produce a summary:
Pipeline: <mode>
Ticket: <JIRA-KEY>
Status: completed|halted
Phases:
- doc-gather: completed (42 files, 85K tokens)
- doc-gap: completed (recommendation: proceed, confidence: 0.82)
- doc-generate: completed (3 modules, avg confidence: 0.85)
- doc-validate: completed (0 high, 3 medium, 5 low findings)
- doc-review: completed (confidence: 0.78)
Output files:
- workspace/context-package.json
- workspace/gap-report.json
- workspace/generated-docs/
- workspace/generation-report.json
- workspace/validation-findings.json
- workspace/review-findings.json
stop (in gap and generate modes)gather-more (in generate mode)After pipeline completes, offer the caller:
/doc-post <PR-URL>tools
Use this skill to filter a pre-fetched set of Hacker News stories down to those that report supply-chain security threats relevant to software developers — including malicious packages on npm or PyPI, compromised developer tooling, and attacks targeting source code repositories or CI/CD infrastructure. Reads stories from stories.json in the workspace, performs semantic analysis (fetching HN threads when the title alone is ambiguous), and writes the stories worth alerting on to findings.json.
development
Run hexora static analysis on a Python package repository to detect suspicious code patterns, then triage findings with deterministic rules and AI reasoning to produce a structured risk report section.
development
Inspect recent git history of a Python package repository for suspicious commits touching supply-chain-sensitive files, then triage findings with AI reasoning to produce a structured risk report section.
development
Scan a Python package repository for compiled/binary files using Fromager-style detection and malcontent YARA analysis, then triage findings with deterministic rules and AI reasoning to produce a structured risk report section.